相关论文: Classifier-free Guidance with Adaptive Scaling

One-step text-to-image generator models offer advantages such as swift inference efficiency, flexible architectures, and state-of-the-art generation performance. In this paper, we study the problem of aligning one-step generator models with…

Generative models are transforming creative domains such as music generation, with inference-time strategies like Classifier-Free Guidance (CFG) playing a crucial role. However, CFG doubles inference cost while limiting originality and…

Safety mechanisms for diffusion and flow models have recently been developed along two distinct paths. In robot planning, control barrier functions are employed to guide generative trajectories away from obstacles at every denoising step by…

Proper guidance strategies are essential to achieve high-quality generation results without retraining diffusion and flow-based text-to-image models. Existing guidance either requires specific training or strong inductive biases of…

Typical diffusion models are trained to accept a particular form of conditioning, most commonly text, and cannot be conditioned on other modalities without retraining. In this work, we propose a universal guidance algorithm that enables…

This paper presents a framework designed to tackle a range of planning problems arise in manipulation, which typically involve complex geometric-physical reasoning related to contact and dynamic constraints. We introduce the Contact Factor…

Image captioning is conventionally formulated as the task of generating captions for images that match the distribution of reference image-caption pairs. However, reference captions in standard captioning datasets are short and may not…

Diffusion models have demonstrated strong generative performance when using guidance methods such as classifier-free guidance (CFG), which enhance output quality by modifying the sampling trajectory. These methods typically improve a target…

Text-to-image diffusion models have emerged as powerful tools for high-quality image generation and editing. Many existing approaches rely on text prompts as editing guidance. However, these methods are constrained by the need for manual…

Although recent text-to-image (T2I) diffusion models excel at aligning generated images with textual prompts, controlling the visual style of the output remains a challenging task. In this work, we propose Style-Prompting Guidance (SPG), a…

Classifier guidance -- using the gradients of an image classifier to steer the generations of a diffusion model -- has the potential to dramatically expand the creative control over image generation and editing. However, currently…

Diffusion-based image editing is a composite process of preserving the source image content and generating new content or applying modifications. While current editing approaches have made improvements under text guidance, most of them have…

Diffusion models have emerged as a powerful framework for generative modeling, with guidance techniques playing a crucial role in enhancing sample quality. Despite their empirical success, a comprehensive theoretical understanding of the…

Consider an auto-regressive model that produces outputs x (e.g., answers to questions, molecules) each of which can be summarized by an attribute vector y (e.g., helpfulness vs. harmlessness, or bio-availability vs. lipophilicity). An…

Classifier guidance is intended to steer a diffusion process such that a given classifier reliably recognizes the generated data point as a certain class. However, most classifier guidance approaches are restricted to robust classifiers,…

Diffusion models deliver high quality in image synthesis but remain expensive during training and inference. Recent works have leveraged the inherent redundancy in visual content to make training more affordable by training only on a subset…

Classifier-free guidance is an effective sampling technique in diffusion models that has been widely adopted. The main idea is to extrapolate the model in the direction of text guidance and away from null-text guidance. In this paper, we…

The advancements in generative modeling, particularly the advent of diffusion models, have sparked a fundamental question: how can these models be effectively used for discriminative tasks? In this work, we find that generative models can…

Diffusion models have seen immense success in modelling continuous data across a range of domains such as vision and audio. Despite the challenges of adapting diffusion models to discrete data, recent work explores their application to text…

We tackle the common challenge of inter-concept visual confusion in compositional concept generation using text-guided diffusion models (TGDMs). It becomes even more pronounced in the generation of customized concepts, due to the scarcity…